[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[HTCondor-users] "GGT GGT GGT about to set io wait" in StarterLog.slot1_1




Dear HTCondor-people,

Does anyone know that the above cryptic message means?  I see it repeatedly in
GPU-jobs, often in long repeated series, where the value always increases; often
it ends in the job crashing.

[root@bornholm condor]# ls -l StarterLog.slot1_1
-rw-r--r-- 1 condor condor 1762008 Jan 28 07:10 StarterLog.slot1_1

[root@bornholm condor]# less StarterLog.slot1_1
01/28/19 04:10:36 (pid:31752) Running job as user xxxxxxxxx
01/28/19 04:10:36 (pid:31752) Create_Process succeeded, pid=31763
01/28/19 04:10:36 (pid:31752) Limiting (soft) memory usage to 0 bytes
01/28/19 04:10:36 (pid:31752) Limiting memsw usage to 9223372036854775807 bytes
01/28/19 04:10:36 (pid:31752) Limiting (soft) memory usage to 6442450944 bytes
01/28/19 04:10:36 (pid:31752) Limiting (hard) memory usage to 50991169536 bytes
01/28/19 04:10:36 (pid:31752) Limiting memsw usage to 50991173632 bytes
01/28/19 04:10:44 (pid:31752) GGT GGT GGT about to set io wait to 1.30623
01/28/19 04:10:44 (pid:31752) GGT GGT GGT about to set io wait to 1.30623
[...]
Few 100 lines deleted
[...]
01/28/19 07:06:02 (pid:31752) GGT GGT GGT about to set io wait to 339.385
01/28/19 07:06:02 (pid:31752) GGT GGT GGT about to set io wait to 339.385
01/28/19 07:10:43 (pid:31752) Process exited, pid=31763, status=0
01/28/19 07:10:43 (pid:31752) GGT GGT GGT about to set io wait to 666.66
01/28/19 07:10:43 (pid:31752) GGT GGT GGT about to set io wait to 666.66
01/28/19 07:10:43 (pid:31752) All jobs have exited... starter exiting

Greetings, Bert.